arxiv:2607.18217
Yiyang CAI
yychai
AI & ML interests
Computer Vision, Generative Models, Image and Video Generation
Recent Activity
authored a paper 6 days ago
HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enchancement authored a paper 6 days ago
DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation authored a paper 6 days ago
Graceful Forgetting in Generative Language ModelsOrganizations
